Files
pipecat/examples/foundational/26c-gemini-multimodal-live-video.py
2024-12-11 11:36:38 -05:00

116 lines
3.7 KiB
Python

#
# Copyright (c) 2024, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import os
import sys
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
async def main():
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=24000,
audio_out_enabled=True,
vad_enabled=True,
vad_audio_passthrough=True,
# set stop_secs to something roughly similar to the internal setting
# of the Multimodal Live api, just to align events. This doesn't really
# matter because we can only use the Multimodal Live API's phrase
# endpointing, for now.
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
start_audio_paused=True,
start_video_paused=True,
),
)
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
# system_instruction="Talk like a pirate."
transcribe_user_audio=True,
transcribe_model_audio=True,
# inference_on_context_initialization=False,
)
context = OpenAILLMContext(
[
{
"role": "user",
"content": "Say hello.",
},
],
)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
# Enable both camera and screenshare. From the client side
# send just one.
await transport.capture_participant_video(
participant["id"], framerate=1, video_source="camera"
)
await transport.capture_participant_video(
participant["id"], framerate=1, video_source="screenVideo"
)
await task.queue_frames([context_aggregator.user().get_context_frame()])
await asyncio.sleep(3)
logger.debug("Unpausing audio and video")
llm.set_audio_input_paused(False)
llm.set_video_input_paused(False)
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())